Version 1.7.5 of the BAS package adds an internal
function to count the number of models that satisfy “hereditary”
constraints. This is used in the force.heredity option in
bas.lm to reduce the number of models considered in the
sampling process and should reduce the memory requirements and speed up
the sampling process. This currently works only for factors included in
the model formula, but not with factors always included in the model
orwith other hereditaty constraints such as with polynomials.
(theforce.heredity option does work with these other
constraints). This is a first step in reducing the number of models
aallocated in the sampling process. Future updates will include other
hereditary constraints.
added hexagon sticker
add copyright to source files to satisfy OpenSSF Best Practice
fixed (issue #89) reported as Error on CRAN Check page for
compiling BAS under R-devel with clang19. Removed legacy definitions of
MACHEPS and MAXNUM from Cephes and replaced
with DLB_EPSILON and DBL_MAX in
R. Files in src/ mconf.h and
const.c are no longer used and will be reomved from in the
future.
fixed (issue #87) prior inclusion probabilities using a Bernoulli
prior other than 0.5 were incorrect if include.always was
used to include some variables always.
Added unit test in test-priorprobs.R
SETLENGTH (issue #82) to
address stack imbalance issues seen in interactive checks and not
flagged in R CMD check.added method="AMCMC" for bas.lm to use
adaptive independent Metropolis Hastings for sampling models. With
option importance.sampling = TRUE the adaptive independent
proposal and be used for importance sampling with improved estimation of
model probabilities and inclusion probabilities based on the
Horivitz-Thompsom / Hajek estimator.
added unit tests for link functions implemented in
family.c
fixed (issue #81) Removed legacy definitions of ‘PI’ and ‘Free’ and replaced with‘M_PI’ and ‘R_Free’ to comply with ‘STRICT_R_HEADERS’ prevent package removal on 9/23/2024
fixed (issue #82) avoid SETLENGTH as non-API function when truncating vectors
Initialized vector se via memset and
disp = 1.0 in fit_glm.c (issue #72)
Initialized variables in hyp1f1.c from
testthat (issue #75)
Removed models that have zero prior probability in
bas.lm and bas.glm (issue #74)
Fixed error in bayesglm.fit to check arguments
x or y for correct type before calling C and
added unit test (issue #67)
Added support for Gamma regression for
bas.glm, with unit tests and example (Code contributed by
@betsyberrson)
added error if supplied initial model for the bas.lm
sampling methods “MCMC” and “MCMC+BAS” had prior probability
zero.
fixed printing problems as identified via checks
fixed indexing error for bas.lm and
method = "MCMC+BAS" as bas.lm using
method = "MCMC+BAS" crashed with a segmentation fault if
bestmodel is not NULL or the null model. GitHub issue
#69
fixed error in predict.bas with
se.fit=TRUE if there is only one predictor. GitHub issue
#68 reported by @AleCarminati added unit test to
test-predict.R
Fixed error in coef for bas.glm objects
when using a betaprior of class IC, including AIC and BIC
Github issue #65
Fixed error when using Jeffreys prior in
bas.glm with the include.always option and
added unit test in test-bas-glm.R.
Github issue #61
Fixed error for extracting coefficients from the median
probability model when a formula is passed as an object rather than a
literal, and added a unit test to test-coefficients.R
Github issues #39 and #56
pivot=FALSE for bas.lm as
default uses pivoting and documentation indicates that
pivot=FALSE should only be used in the full rank case so
that users should not encounter this issue in practice. Users will
continue to see a warning of NA’s are returned, but should be aware that
not all platforms may produce a warning (such as M1mac). Github issue
#62Added checks and unit-tests to see if modelprior is of class ‘prior’ resolving Github Issue #57
Removed polevl.c, psi.c and
gamma.c from Cephes as no longer used after switching to
R’s internal functions
DOUBLE_EPS with
DBL_EPSILON for R 4.2.0 release (in two places) so restore
on CRANreplaced deprecated DOUBLE_EPS with
DBL_EPSILON for R 4.2.0 release
fixed warnings from CRAN checks for under R devel (use of | and
if with class)
added a function trCCH that uses integration to
compute the normalizing constant in the Truncated Compound Confluent
Hypergeometric distribution that provides the correct normalizing
constant for Gordy (1998) and is more stable for large values compared
to the current phi1 function. This is now used in the
TCCH prior for bas.glm.
Rewrote phi1 function to use direct numerical
integration (phi1_int) when Wald statistic is large so that
marginal likelihoods are not NA as suggested by Daniel Heeman and
Alexander Ly (see below). This should improve stability of estimates of
Bayes Factors and model probabilities from bas.glm that
used the HyperTwo function, including coefficient priors
for hyper.g.n(), robust(), and
intrinsic(). Added additional unit tests.
Added thin as an option for
bas.glm
added unit tests and examples to show the connections between the
special functions trCCH, phi1,
1F1 and 2F1
added internal function for phi1_int when the
original HyperTwo function returns NA Issue #55 See
more details above.
corrected the shrinkage estimate under the CCH prior
that did not include terms involving the beta
function.
USE_FC_LEN_T
for character stringslog_laplace_F21 which had
an uninitialized variable leading to NaN being returned from
R function hypergeometric2F1Fixed WARNING under fedora-clang-devel. Added climate.dat file to package for building vignette so that package does not violate CRAN’s policy for accessing internet resources and is more permanent if file location/url changes locally.
Fixed testthat errors under Solaris. Default settings for
force.heredity is set back to FALSE in bas.lm
and bas.glm so that methods work on all platforms. For
Solaris, users who wish to impose the force.heredity
constraint may use the post-processing function.
Fixed valgrind error in src/ZS_approx_null_np.c for invalid write noted in CRAN checks
fixed function declaration type-mismatch and argument errors identified by LTO noted in CRAN checks
Added contrast=NULL argument to bas.lm
and bas.glm so that non-NULL contrasts do not trigger
warning in model.matrix as of R 3.6.0. Bug
#44
Added check for sample size equal to zero due to subsetting or missing data Bug #37
Fixed errors identified on cran checks https://cran.r-project.org/web/checks/check_results_BAS.html
initialize R2_m = 0.0 in lm_mcmcbas.c (lead to NA’s with clang on debian and fedora )
switch to default of pivot = TRUE in
bas.lm, adding tol as an argument to control
tolerance in cholregpovot for improved stability across
platforms with singular or nearly singular designs.
valgrind messages: Conditional jump or move depends on uninitialized value(s). Initialize vectors allocated via R_alloc in lm_deterministic.c and glm_deterministic.c.
Included an option pivot=TRUE in bas.lm
to fit the models using a pivoted Cholesky decomposition to allow models
that are rank-deficient. Enhancement #24
and Bug #21.
Currently coefficients that are not-estimable are set to zero so that
predict and other methods will work as before. The vector
rank is added to the output (see documentation for
bas.lm) and the degrees of freedom methods that assume a
uniform prior for obtaining estimates (AIC and BIC) are adjusted to use
rank rather than size.
Added option force.heredity=TRUEto force lower order
terms to be included if higher order terms are present (hierarchical
constraint) for method='MCMC' and method='BAS'
with bas.lm and bas.glm. Updated Vignette to
illustrate. enhancement
#19. Checks to see if parents are included using
include.always pass issue
#26.
Added option drop.always.included to
image.bas so that variables that are always included may be
excluded from the image. By default all are shown enhancement
#23
Added option drop.always.included and
subset to plot.bas so that variables that are
always included may be excluded from the plot showing the marginal
posterior inclusion probabilities (which=4). By default all
are shown enhancement
#23
update fitted.bas to use predict so that code covers
both GLM and LM cases with type='link' or
type='response'
Updates to package for CII Best Practices Badge certification
Added Code
Coverage support and more extensive tests using
test_that.
fixed issue #36
Errors in prior = “ZS-null” when R2 is not finite or out of range due to
model being not full rank. Change in gexpectations function
in file bayesreg.c
fixed issue #35 for
method="MCMC+BAS" in bas.glm in
glm_mcmcbas.c when no values are provided for
MCMC.iterations or n.models and defaults are
used. Added unit test in test-bas-glm.R
fixed issue #34 for
bas.glm where variables in include.always had
marginal inclusion probabilities that were incorrect. Added unit test in
test-bas-glm.R
fixed issue #33 for Jeffreys prior where marginal inclusion probabilities were not renormalized after dropping intercept model
fixed issue #32 to
allow vectorization for phi1 function in R/cch.R and added
unit test to “tests/testthat/test-special-functions.R”
fixed issue #31 to
coerce g to be a REAL for g.prior prior and
IC.prior in bas.glm; added unit-test
“tests/testthat/test-bas-glm.R”
fixed issue #30 added
n as hyper-parameter if NULL and coerced to be a REAL for
intrinsic prior in bas.glm; added
unit-test
fixed issue #29 added
n as hyper-parameter if NULL and coerced to be a REAL for
beta.prime prior in bas.glm; added
unit-test
fixed issue #28 fixed length of MCMC estimates of marginal inclusion probabilities; added unit-test
fixed issue #27 where expected shrinkage with the JZS prior was greater than 1. Added unit test.
fixed output include.always to include the intercept
issue #26
always so that drop.always.included = TRUE drops the
intercept and any other variables that are forced in.
include.always and force.heredity=TRUE can now
be used together with method="BAS".
added warning if marginal likelihoods/posterior probabilities are
NA with default model fitting method with suggestion that models be
rerun with pivot = TRUE. This uses a modified Cholesky
decomposition with pivoting so that if the model is rank deficient or
nearly singular the dimensionality is reduced. Bug
#21.
corrected count for first model with method='MCMC'
which lead to potential model with 0 probability and errors in
image.
coerced predicted values to be a vector under BMA (was a matrix)
fixed size with using
method=deterministic in bas.glm (was not
updated)
fixed problem in confint with
horizontal=TRUE when intervals are point mass at
zero.
suppress warning when sampling probabilities are 1
or 0 and the number of models is decremented
Issue
#25
changed force.heredity.bas to re-normalize the prior
probabilities rather than to use a new prior probability based on
heredity constraints. For future, add new priors for models based on
heredity. See comment on issue
#26.
Changed License to GPL 3.0
variable.names to extract variable
names in the highest probability model, median probability model, and
best probability model for objects created by predict.predict.basglm which
had that type = "link" was the default for prediction issue #18add na.action for handling NA’s for predict methods issue #10
added include.always as new argument to
bas.lm. This allows a formula to specify which terms should
always be included in all models. By default the intercept is always
included.
added a section to the vignette to illustrate weighted regression
and the force.heredity.bas function to group levels of a
factor so that they enter or leave the model together.
fixed problem if there is only one model for image
function;
github issue
#11
fixed error in bas.lm with non-equal weights where
R2 was incorrect. issue #17 ##
Deprecated
deprecate the predict argument in
predict.bas, predict.basglm and internal
functions as it is not utilized
confint.coef.bas when parm is a character
stringBayes.outlier if prior
probability of no outliers is providedfixed issue with scoping in eval of data in
predict.bas if dataname is defined in local env.
fixed issue 10 in github (predict for estimator=‘BPM’ failed if there were NA’s in the X data. Delete NA’s before finding the closest model.
fixed bug in ‘JZS’ prior - merged pull request #12 from vandenman/master
fixed bug in bas.glm when default betaprior (CCH) is used and inputs were INTEGER instead of REAL
removed warning with use of ‘ZS-null’ for backwards compatibility
updated print.bas to reflect changes in print.lm
Added Bayes.outlier function to calculate posterior probabilities of outliers using the method from Chaloner & Brant for linear models.
Added new method for bas.lm to obtain marginal
likelihoods with the Zellner-Siow Priors for “prior= ‘JZS’ using
QUADPATH routines for numerical integration. The optional hyper
parameter alpha may now be used to adjust the scaling of the ZS prior
where g ~ G(1/2, alpha*n/2) as in the BayesFactor package
of Morey, with a default of alpha=1 corresponding to the ZS prior used
in Liang et al (2008). This also uses more stable evaluations of log(1 +
x) to prevent underflow/overflow.
Priors ZS-full for bas.lm is planned to be
deprecated.
replaced math functions to use portable C code from Rmath and consolidated header files
Fixed unprotected ANS in C code in glm_sampleworep.c and sampleworep.c after call to PutRNGstate and possible stack imbalance in glm_mcmc.
Fixed problem with predict for estimator=BPM when newdata was one row
Fixed non-conformable error with predict when new
data was from a dataframe with one row.
Fixed problem with missing weights for prediction using the median probability model with no new data.
Extract coefficient summaries, credible intervals and plots for
the HPM and MPM in addition to the default
BMA by adding a new estimator argument to the
coef function. The new n.models argument to
coef provides summaries based on the top
n.models highest probability models to reduce computation
time. ‘n.models = 1’ is equivalent to the highest probability
model.
use of newdata that is a vector is now deprecated for predict.bas; newdata must be a dataframe or missing, in which case fitted values based on the dataframe used in fitting is used
factor levels are handled as in lm or
glm for prediction when there may be only level of a factor
in the newdata
fixed issue for prediction when newdata has just one row
fixed missing id in plot.bas for which=3
bas.lm to agree with
documentationrenormalize that selects
whether the Monte Carlo frequencies are used to estimate posterior model
and marginal inclusion probabilities (default
renormalize = FALSE) or that marginal likelihoods time
prior probabilities that are renormalized to sum to 1 are used. (the
latter is the only option for the other methods); new slots for
probne0.MCMC, probne0.RN, postprobs.RN and postprobs.MCMC.coefficients function.bas.lm and
bas.glmna.action for bas.lm and
bas.glm to omit missing data.confint.pred.bas or confint.coef.bas. See the
help files for an example or the vignette.se.fit option in
predict.basglm.testBF as a betaprior option for
bas.glm to implement Bayes Factors based on the likelihood
ratio statistic’s distribution for GLMs.A vignette has been added at long last! This illustrates several of
the new features in BAS such as
confint.pred.bas()confint.coef.bas()predict.bas()type to specify estimator in
fitted.bas and replaced with estimator so that
predict() and fitted() are compatible with
other S3 methods.bas to avoid NAMESPACE
conflicts with other librariesfitted.bas or predict.basbas.glmdiagnostic() function for checking convergence of
bas objects created with method = "MCMC"”plot.bas that appears with Sweavecoef.bma when there is just one
predictorbas
rather than bma to avoid name conflicts with other
packages- added weights for linear models
- switched LINPACK calls in bayesreg to LAPACK finally should be
faster
- fixed bug in intercept calculation for glms
- fixed inclusion probabilities to be a vector in the global EB
methods for linear models- added intrinsic prior for GLMs
- fixed problems for linear models for p > n and R2 not correct- added phi1 function from Gordy (1998) confluent hypergeometric
function of two variables also known as one of the Horn
hypergeometric functions or Humbert's phi1
- added Jeffrey's prior on g
- added the general tCCH prior and special cases of the hyper-g/n.
- TODO check shrinkage functions for all - new improved Laplace approximation for hypergeometric1F1
- added class basglm for predict
- predict function now handles glm output
- added dataframe option for newdata in predict.bas and predict.basglm
- renamed coefficients in output to be 'mle' in bas.lm to be consistent across
lm and glm versions so that predict methods can handle both
cases. (This may lead to errors in other external code that
expects object$ols or object$coefficients)
- fixed bug with initprobs that did not include an intercept for bas.lm- added thinning option for MCMC method for bas.lm
- returned posterior expected shrinkage for bas.glm
- added option for initprobs = "marg-eplogp" for using marginal
SLR models to create starting probabilities or order variables
especially for p > n case
- added standalone function for hypergeometric1F1 using Cephes
library and a Laplace approximation
-Added class "BAS" so that predict and fitted functions (S3
methods) are not masked by functions in the BVS package: to do
modify the rest of the S3 methods.- added bas.glm for model averaging/section using mixture of g-priors for
GLMs. Currently limited to Logistic Regression
- added Poisson family for glm.fit- cleaned up MCMC method code- removed internal print statements in bayesglm.c
- Bug fixes in AMCMC algorithm- fixed glm-fit.R so that hyper parameter for BIC is numeric- added new AMCMC algorithm- bug fix in bayes.glm- added C routines for fitting glms- fixed problem with duplicate models if n.models was > 2^(p-1) byrestricting n.models
- save original X as part of object so that fitted.bma gives thecorrect fitted values (broken in version 0.80)
- Added `hypergeometric2F1` function that is callable by R
- centered X's in bas.lm so that the intercept has the correctshrinkage - changed predict.bma to center newdata using
the mean(X) - Added new Adaptive MCMC option (method = “AMCMC”) (this is
not stable at this point)
-Allowed pruning of model tree to eliminate rejected models- Added MCMC option to create starting values for BAS (`method = "MCMC+BAS"`)-Cleaned up all .Call routines so that all objects are duplicated orallocated within code
- fixed ch2inv that prevented building on Windows in bayes glm_fit- fixed FORTRAN calls to use F77_NAME macro
- changed allocation of objects for .Call to prevent some objects from being overwritten. - fixed EB.global function to include prior probabilities on models
- fixed update function - fixed predict.bma to allow newdata to be a matrix or vector with thecolumn of ones for the intercept optionally included. - fixed help file for predict - added modelprior argument to bas.lm so that users may now use the beta-binomial prior distribution on model size in addition to the default uniform distribution - added functions uniform(), beta-binomial() and Bernoulli() to create model prior objects - added a vector of user specified initial probabilities as an option for argument initprobs in bas.lm and removed the separate argument user.prob